Created
March 13, 2014 08:07
-
-
Save nickjacob/9524028 to your computer and use it in GitHub Desktop.
merge a series of level dbs to provide an output db of a specified length
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env perl | |
use strict; | |
use warnings; | |
use Tie::LevelDB; | |
sub foreach_key { | |
my ($db_name, $block) = @_; | |
my $db = new Tie::LevelDB::DB($db_name); | |
my $it = $db->NewIterator; | |
for ($it->SeekToFirst; $it->Valid; $it->Next) { | |
return 1 if $block->($it->key, $it->value) == 0; | |
} | |
return 0; | |
} | |
unless (caller) { | |
my ($count, $output, @dbs) = @ARGV; | |
if (!$count || !$output) { | |
print STDERR "usage: <output count> <output db name> [source...]\n"; | |
exit 2; | |
} | |
my $out_db = new Tie::LevelDB::DB($output); | |
my $current = 0; | |
foreach my $db (@dbs) { | |
print "working with: $db\n"; | |
my $ret = foreach_key($db, my $s = sub { | |
my ($k, $v) = @_; | |
$out_db->Put($k, $v); | |
return (++$current == $count) ? 0 : 1; | |
}); | |
if ($ret == 1) { | |
print "finished - enough data!\n"; | |
last;; | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment